Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    each

    np_max-act · gemini-2.0-flash

    The neuron never fires—it’s effectively inactive and does not detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Inspectable
    -0.07
    .DataPropertyName
    -0.07
    การใช
    -0.06
    (Clone
    -0.06
     заклад
    -0.06
     betrayal
    -0.06
    _annotations
    -0.06
     Кат
    -0.06
    気に入
    -0.06
    قيقة
    -0.06
    POSITIVE LOGITS
     che
    0.07
     sucked
    0.06
    arching
    0.06
    matcher
    0.06
     віт
    0.06
     Camp
    0.06
    xies
    0.06
     reload
    0.06
    оят
    0.06
     mt
    0.06
    Act Density 0.013%

    No Known Activations